An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not nece
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly sc
Troubling Trends in Machine Learning Scholarship
By Zachary C. Lipton* & Jacob Steinhardt* *equal authorship Originally presented at ICML 2018: Machine Learning Debates [arXiv link] Published in Communications of the ACM 1 Introduction Collectively, machine learning (ML) researchers are engaged in the creation and dissemination of knowledge about data-driven algorithms. In a given paper, researchers might aspire to any subset of the following
ICML 2019 Meta-Learning Tutorial
Chelsea Finn is a research scientist at Google Brain and a post-doctoral scholar at UC Berkeley. In September 2019, she will be joining Stanford's computer science department as an assistant professor. Finn's research interests lie in the ability to enable robots and other agents to develop broadly intelligent behavior through learning and interaction. To this end, Finn has developed deep learning
Making Netflix Machine Learning Algorithms Reliable
This document discusses making Netflix machine learning algorithms reliable. It describes how Netflix uses machine learning for tasks like personalized ranking and recommendation. The goals are to maximize member satisfaction and retention. The models and algorithms used include regression, matrix factorization, neural networks, and bandits. The key aspects of making the models reliable discussed
Google Sites: Sign-in
Not your computer? Use a private browsing window to sign in. Learn more
Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification
Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification Zhiwu Huang†‡ ZHIWU.HUANG@VIPL.ICT.AC.CN Ruiping Wang†§ WANGRUIPING@ICT.AC.CN Shiguang Shan†§ SGSHAN@ICT.AC.CN Xianqiu Li†‡ XIANQIU.LI@VIPL.ICT.AC.CN Xilin Chen†§ XLCHEN@ICT.AC.CN † Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of
A Neural Conversational Model
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require hand-crafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by p
Building high-level features using large scale unsupervised learning
We consider the problem of building highlevel, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder with pooling and local contrast normalization on a large dataset of images (the model has 1 billion connections, the dataset has 10 million
ICML 2014 Review
ICML 2014 went well, kudos to the organizers. The location (Beijing) and overlap with CVPR definitely impacted the distribution of attendees, so the conference felt different than last year. (I also learned that my blog is blocked from China, collateral damage from some kind of spat between Google and the Chinese government). Deep learning was by far the most popular conference track, to the exten
Machine Learning that Matters(ICML 2012) 読んだ - 糞糞糞ネット弁慶
機械学習やってる人は皆読むべきだと思う． Machine Learning that Matters (pdf) 概要 機械学習のトップカンファレンスICMLに数式/アルゴリズム/定理を1つも書かずに通った論文． 機械学習は何のために重要なのか，現実世界との繋がりを失っていないか，あなたは「機械学習って何の役に立つの?」と聞かれた時にちゃんと答えられるのか，まだ取り組まれてない重要な問題は何か，について触れた長文ブログのような論文． contributionsは 機械学習の研究と人類と科学全体におけるもっと大きな研究との間にある欠落に対する明確な特定と解説 そのギャップに取り組むための第一歩 (どう訳していいかわからなかった) 機械学習において重要な問題の提示 機械学習のための機械学習(要約: マッシュルームやアヤメの分類器を死ぬほど作って何の役に立ったの？) ベンチマークデータの問題 こ
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
http://kaiminghe.com/icml16tutorial/icml2016_tutorial_deep_residual_networks_kaiminghe.pdf